{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/extending-conditional-convolution-structures","title":"EXTENDING CONDITIONAL CONVOLUTION STRUCTURES FOR ENHANCING MULTITASKING CONTINUAL LEARNING","arxiv_id":null,"date":"2020-12-07","proceeding":null,"authors":["Cheng-Hao Tu","Cheng-En Wu","Chu-Song Chen"],"abstract":"Conditional operations have received much attention in recent deep learning studies to facilitate the prediction accuracy of a model. A recent advance toward this direction is the conditional parametric convolutions (CondConv), which is proposed to exploit additional capacities provided by the deep model weights to enhance the performance, whereas the computational complexity of the model is much less influenced. CondConv employs input-dependent fusion parameters that can combine multiple columns of convolution kernels adaptively for performance improvement. At runtime, the columns of kernels are on-line combined into a single one, and thus the time complexity is much less than that of employing multiple columns in a convolution layer under the same capacity. Although CondConv is effective for the performance enhancement of a deep model, it is currently applied to individual tasks only. As it has the nice property of adding model weights with computational efficiency, we extend it for multi-task learning, where the tasks are presented incrementally. In this work, we introduce a sequential multi-task (or continual) learning approach based on the CondConv structures, referred to as CondConv-Continual. Experimental results show that the proposed approach is effective for unforgetting continual learning. Compared to current approaches, CondConv is advantageous to offer a regular and easy-to-implement way to enlarge the neural networks for acquiring additional capacity and provides a cross-referencing mechanism for different task models to achieve comparative results.","url_abs":"http://www.apsipa.org/proceedings/2020/pdfs/0001605.pdf","url_pdf":"http://www.apsipa.org/proceedings/2020/pdfs/0001605.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"extending-conditional-convolution-structures","repo_url":"https://github.com/ivclab/CondConvContinual","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"condconv","method_name":"CondConv"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/continual-learning-on-cubs-fine-grained-6","task":"Continual Learning","dataset":"CUBS (Fine-grained 6 Tasks)","model":"CondConvContinual","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"84.26"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-cifar100-20-tasks","task":"Continual Learning","dataset":"Cifar100 (20 tasks)","model":"CondConvContinual","rank_in_archive_order":6,"of":9,"metrics":{"Average Accuracy":"77.4"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-cifar100-20-tasks","task":"Continual Learning","dataset":"Cifar100 (20 tasks)","model":"CPG-light","rank_in_archive_order":8,"of":9,"metrics":{"Average Accuracy":"77.0"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-flowers-fine-grained-6","task":"Continual Learning","dataset":"Flowers (Fine-grained 6 Tasks)","model":"CondConvContinual","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"97.16"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-imagenet-fine-grained-6","task":"Continual Learning","dataset":"ImageNet (Fine-grained 6 Tasks)","model":"CondConvContinual","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy":"76.16"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-imagenet-50-5-tasks","task":"Continual Learning","dataset":"ImageNet-50 (5 tasks)","model":"CondConvContinual","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"61.32"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-sketch-fine-grained-6","task":"Continual Learning","dataset":"Sketch (Fine-grained 6 Tasks)","model":"CondConvContinual","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"80.77"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-stanford-cars-fine","task":"Continual Learning","dataset":"Stanford Cars (Fine-grained 6 Tasks)","model":"CondConvContinual","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"92.61"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-wikiart-fine-grained-6","task":"Continual Learning","dataset":"Wikiart (Fine-grained 6 Tasks)","model":"CondConvContinual","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"78.32"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"ivclab/CondConvContinual","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"38aeff6e640abb5715b62d63d0d242e9d1e9c0c94c8c8a8ff5fe34470e99881a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}